Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13921
    Prev
    Next
    INDEX
    Explanations

    information related to diplomatic relations and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to political events or discussions involving Trump and Kim

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.70
     "$:/
    -0.61
     Surviv
    -0.59
    vertisements
    -0.58
     pursu
    -0.58
     Styles
    -0.56
     fielded
    -0.55
     Alternate
    -0.55
    intosh
    -0.55
    Contents
    -0.55
    POSITIVE LOGITS
    ophen
    0.69
     Lavrov
    0.67
    Ħ¢
    0.66
     Kislyak
    0.66
     Dalai
    0.62
     pope
    0.61
     quake
    0.61
     Maduro
    0.60
    ?]
    0.58
     probe
    0.56
    Activations Density 0.019%

    No Known Activations